© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 107508
    Prev
    Next
    INDEX
    Explanations

    language proficiency levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    小說
    0.49
     دائ
    0.48
    过
    0.46
    问题
    0.46
    毕业
    0.46
    农
    0.46
    揀
    0.46
    埆
    0.45
    作为一个
    0.45
     Kelas
    0.45
    POSITIVE LOGITS
     manicure
    0.62
     paves
    0.61
     parquet
    0.60
     nanofibers
    0.57
     tableware
    0.56
     comen
    0.56
     fract
    0.55
     cree
    0.54
     radiant
    0.54
     multicultural
    0.54
    Activations Density 0.000%

    No Known Activations